discourse/spec/requests/robots_txt_controller_spec.rb

73 lines
2.8 KiB
Ruby

require 'rails_helper'
RSpec.describe RobotsTxtController do
describe '#index' do
context 'allow_index_in_robots_txt is true' do
def expect_allowed_and_disallowed_sections(allow_index, disallow_index)
expect(allow_index).to be_present
expect(disallow_index).to be_present
allow_section = allow_index < disallow_index ?
response.body[allow_index...disallow_index] : response.body[allow_index..-1]
expect(allow_section).to include('Disallow: /u/')
expect(allow_section).to_not include("Disallow: /\n")
disallowed_section = allow_index < disallow_index ?
response.body[disallow_index..-1] : response.body[disallow_index...allow_index]
expect(disallowed_section).to include("Disallow: /\n")
end
it "returns index when indexing is allowed" do
SiteSetting.allow_index_in_robots_txt = true
get '/robots.txt'
i = response.body.index('User-agent: *')
expect(i).to be_present
expect(response.body[i..-1]).to include("Disallow: /u/")
end
it "can whitelist user agents" do
SiteSetting.whitelisted_crawler_user_agents = "Googlebot|Twitterbot"
get '/robots.txt'
expect(response.body).to include('User-agent: Googlebot')
expect(response.body).to include('User-agent: Twitterbot')
allowed_index = [response.body.index('User-agent: Googlebot'), response.body.index('User-agent: Twitterbot')].min
disallow_all_index = response.body.index('User-agent: *')
expect_allowed_and_disallowed_sections(allowed_index, disallow_all_index)
end
it "can blacklist user agents" do
SiteSetting.blacklisted_crawler_user_agents = "Googlebot|Twitterbot"
get '/robots.txt'
expect(response.body).to include('User-agent: Googlebot')
expect(response.body).to include('User-agent: Twitterbot')
disallow_index = [response.body.index('User-agent: Googlebot'), response.body.index('User-agent: Twitterbot')].min
allow_index = response.body.index('User-agent: *')
expect_allowed_and_disallowed_sections(allow_index, disallow_index)
end
it "ignores blacklist if whitelist is set" do
SiteSetting.whitelisted_crawler_user_agents = "Googlebot|Twitterbot"
SiteSetting.blacklisted_crawler_user_agents = "Bananabot"
get '/robots.txt'
expect(response.body).to_not include('Bananabot')
expect(response.body).to include('User-agent: Googlebot')
expect(response.body).to include('User-agent: Twitterbot')
end
end
it "returns noindex when indexing is disallowed" do
SiteSetting.allow_index_in_robots_txt = false
get '/robots.txt'
expect(response.body).to_not include("Disallow: /u/")
end
end
end